Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from David Miller:

 1) Support 6Ghz band in ath11k driver, from Rajkumar Manoharan.

 2) Support UDP segmentation in code TSO code, from Eric Dumazet.

 3) Allow flashing different flash images in cxgb4 driver, from Vishal
    Kulkarni.

 4) Add drop frames counter and flow status to tc flower offloading,
    from Po Liu.

 5) Support n-tuple filters in cxgb4, from Vishal Kulkarni.

 6) Various new indirect call avoidance, from Eric Dumazet and Brian
    Vazquez.

 7) Fix BPF verifier failures on 32-bit pointer arithmetic, from
    Yonghong Song.

 8) Support querying and setting hardware address of a port function via
    devlink, use this in mlx5, from Parav Pandit.

 9) Support hw ipsec offload on bonding slaves, from Jarod Wilson.

10) Switch qca8k driver over to phylink, from Jonathan McDowell.

11) In bpftool, show list of processes holding BPF FD references to
    maps, programs, links, and btf objects. From Andrii Nakryiko.

12) Several conversions over to generic power management, from Vaibhav
    Gupta.

13) Add support for SO_KEEPALIVE et al. to bpf_setsockopt(), from Dmitry
    Yakunin.

14) Various https url conversions, from Alexander A. Klimov.

15) Timestamping and PHC support for mscc PHY driver, from Antoine
    Tenart.

16) Support bpf iterating over tcp and udp sockets, from Yonghong Song.

17) Support 5GBASE-T i40e NICs, from Aleksandr Loktionov.

18) Add kTLS RX HW offload support to mlx5e, from Tariq Toukan.

19) Fix the ->ndo_start_xmit() return type to be netdev_tx_t in several
    drivers. From Luc Van Oostenryck.

20) XDP support for xen-netfront, from Denis Kirjanov.

21) Support receive buffer autotuning in MPTCP, from Florian Westphal.

22) Support EF100 chip in sfc driver, from Edward Cree.

23) Add XDP support to mvpp2 driver, from Matteo Croce.

24) Support MPTCP in sock_diag, from Paolo Abeni.

25) Commonize UDP tunnel offloading code by creating udp_tunnel_nic
    infrastructure, from Jakub Kicinski.

26) Several pci_ --> dma_ API conversions, from Christophe JAILLET.

27) Add FLOW_ACTION_POLICE support to mlxsw, from Ido Schimmel.

28) Add SK_LOOKUP bpf program type, from Jakub Sitnicki.

29) Refactor a lot of networking socket option handling code in order to
    avoid set_fs() calls, from Christoph Hellwig.

30) Add rfc4884 support to icmp code, from Willem de Bruijn.

31) Support TBF offload in dpaa2-eth driver, from Ioana Ciornei.

32) Support XDP_REDIRECT in qede driver, from Alexander Lobakin.

33) Support PCI relaxed ordering in mlx5 driver, from Aya Levin.

34) Support TCP syncookies in MPTCP, from Flowian Westphal.

35) Fix several tricky cases of PMTU handling wrt. briding, from Stefano
    Brivio.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2056 commits)
  net: thunderx: initialize VF's mailbox mutex before first usage
  usb: hso: remove bogus check for EINPROGRESS
  usb: hso: no complaint about kmalloc failure
  hso: fix bailout in error case of probe
  ip_tunnel_core: Fix build for archs without _HAVE_ARCH_IPV6_CSUM
  selftests/net: relax cpu affinity requirement in msg_zerocopy test
  mptcp: be careful on subflow creation
  selftests: rtnetlink: make kci_test_encap() return sub-test result
  selftests: rtnetlink: correct the final return value for the test
  net: dsa: sja1105: use detected device id instead of DT one on mismatch
  tipc: set ub->ifindex for local ipv6 address
  ipv6: add ipv6_dev_find()
  net: openvswitch: silence suspicious RCU usage warning
  Revert "vxlan: fix tos value before xmit"
  ptp: only allow phase values lower than 1 period
  farsync: switch from 'pci_' to 'dma_' API
  wan: wanxl: switch from 'pci_' to 'dma_' API
  hv_netvsc: do not use VF device if link is down
  dpaa2-eth: Fix passing zero to 'PTR_ERR' warning
  net: macb: Properly handle phylink on at91sam9x
  ...

4 files changed, 110 insertions, 11 deletions

diff --git a/arch/arm64/include/asm/extable.h b/arch/arm64/include/asm/extable.h
index 56a4f68b262e..840a35ed92ec 100644
--- a/arch/arm64/include/asm/extable.h
+++ b/arch/arm64/include/asm/extable.h
@@ -22,5 +22,17 @@ struct exception_table_entry
 
 #define ARCH_HAS_RELATIVE_EXTABLE
 
+#ifdef CONFIG_BPF_JIT
+int arm64_bpf_fixup_exception(const struct exception_table_entry *ex,
+			      struct pt_regs *regs);
+#else /* !CONFIG_BPF_JIT */
+static inline
+int arm64_bpf_fixup_exception(const struct exception_table_entry *ex,
+			      struct pt_regs *regs)
+{
+	return 0;
+}
+#endif /* !CONFIG_BPF_JIT */
+
 extern int fixup_exception(struct pt_regs *regs);
 #endif
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index c760b9e159f5..17e81bd9a2d3 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -599,9 +599,9 @@ __SYSCALL(__NR_recvfrom, compat_sys_recvfrom)
 #define __NR_shutdown 293
 __SYSCALL(__NR_shutdown, sys_shutdown)
 #define __NR_setsockopt 294
-__SYSCALL(__NR_setsockopt, compat_sys_setsockopt)
+__SYSCALL(__NR_setsockopt, sys_setsockopt)
 #define __NR_getsockopt 295
-__SYSCALL(__NR_getsockopt, compat_sys_getsockopt)
+__SYSCALL(__NR_getsockopt, sys_getsockopt)
 #define __NR_sendmsg 296
 __SYSCALL(__NR_sendmsg, compat_sys_sendmsg)
 #define __NR_recvmsg 297
diff --git a/arch/arm64/mm/extable.c b/arch/arm64/mm/extable.c
index 81e694af5f8c..eee1732ab6cd 100644
--- a/arch/arm64/mm/extable.c
+++ b/arch/arm64/mm/extable.c
@@ -11,8 +11,14 @@ int fixup_exception(struct pt_regs *regs)
 	const struct exception_table_entry *fixup;
 
 	fixup = search_exception_tables(instruction_pointer(regs));
-	if (fixup)
-		regs->pc = (unsigned long)&fixup->fixup + fixup->fixup;
+	if (!fixup)
+		return 0;
 
-	return fixup != NULL;
+	if (IS_ENABLED(CONFIG_BPF_JIT) &&
+	    regs->pc >= BPF_JIT_REGION_START &&
+	    regs->pc < BPF_JIT_REGION_END)
+		return arm64_bpf_fixup_exception(fixup, regs);
+
+	regs->pc = (unsigned long)&fixup->fixup + fixup->fixup;
+	return 1;
 }
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 3cb25b43b368..f8912e45be7a 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -7,6 +7,7 @@
 
 #define pr_fmt(fmt) "bpf_jit: " fmt
 
+#include <linux/bitfield.h>
 #include <linux/bpf.h>
 #include <linux/filter.h>
 #include <linux/printk.h>
@@ -56,6 +57,7 @@ struct jit_ctx {
 	int idx;
 	int epilogue_offset;
 	int *offset;
+	int exentry_idx;
 	__le32 *image;
 	u32 stack_size;
 };
@@ -351,6 +353,67 @@ static void build_epilogue(struct jit_ctx *ctx)
 	emit(A64_RET(A64_LR), ctx);
 }
 
+#define BPF_FIXUP_OFFSET_MASK	GENMASK(26, 0)
+#define BPF_FIXUP_REG_MASK	GENMASK(31, 27)
+
+int arm64_bpf_fixup_exception(const struct exception_table_entry *ex,
+			      struct pt_regs *regs)
+{
+	off_t offset = FIELD_GET(BPF_FIXUP_OFFSET_MASK, ex->fixup);
+	int dst_reg = FIELD_GET(BPF_FIXUP_REG_MASK, ex->fixup);
+
+	regs->regs[dst_reg] = 0;
+	regs->pc = (unsigned long)&ex->fixup - offset;
+	return 1;
+}
+
+/* For accesses to BTF pointers, add an entry to the exception table */
+static int add_exception_handler(const struct bpf_insn *insn,
+				 struct jit_ctx *ctx,
+				 int dst_reg)
+{
+	off_t offset;
+	unsigned long pc;
+	struct exception_table_entry *ex;
+
+	if (!ctx->image)
+		/* First pass */
+		return 0;
+
+	if (BPF_MODE(insn->code) != BPF_PROBE_MEM)
+		return 0;
+
+	if (!ctx->prog->aux->extable ||
+	    WARN_ON_ONCE(ctx->exentry_idx >= ctx->prog->aux->num_exentries))
+		return -EINVAL;
+
+	ex = &ctx->prog->aux->extable[ctx->exentry_idx];
+	pc = (unsigned long)&ctx->image[ctx->idx - 1];
+
+	offset = pc - (long)&ex->insn;
+	if (WARN_ON_ONCE(offset >= 0 || offset < INT_MIN))
+		return -ERANGE;
+	ex->insn = offset;
+
+	/*
+	 * Since the extable follows the program, the fixup offset is always
+	 * negative and limited to BPF_JIT_REGION_SIZE. Store a positive value
+	 * to keep things simple, and put the destination register in the upper
+	 * bits. We don't need to worry about buildtime or runtime sort
+	 * modifying the upper bits because the table is already sorted, and
+	 * isn't part of the main exception table.
+	 */
+	offset = (long)&ex->fixup - (pc + AARCH64_INSN_SIZE);
+	if (!FIELD_FIT(BPF_FIXUP_OFFSET_MASK, offset))
+		return -ERANGE;
+
+	ex->fixup = FIELD_PREP(BPF_FIXUP_OFFSET_MASK, offset) |
+		    FIELD_PREP(BPF_FIXUP_REG_MASK, dst_reg);
+
+	ctx->exentry_idx++;
+	return 0;
+}
+
 /* JITs an eBPF instruction.
  * Returns:
  * 0  - successfully JITed an 8-byte eBPF instruction.
@@ -375,6 +438,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 	u8 jmp_cond, reg;
 	s32 jmp_offset;
 	u32 a64_insn;
+	int ret;
 
 #define check_imm(bits, imm) do {				\
 	if ((((imm) > 0) && ((imm) >> (bits))) ||		\
@@ -694,7 +758,6 @@ emit_cond_jmp:
 		const u8 r0 = bpf2a64[BPF_REG_0];
 		bool func_addr_fixed;
 		u64 func_addr;
-		int ret;
 
 		ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass,
 					    &func_addr, &func_addr_fixed);
@@ -738,6 +801,10 @@ emit_cond_jmp:
 	case BPF_LDX | BPF_MEM | BPF_H:
 	case BPF_LDX | BPF_MEM | BPF_B:
 	case BPF_LDX | BPF_MEM | BPF_DW:
+	case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
+	case BPF_LDX | BPF_PROBE_MEM | BPF_W:
+	case BPF_LDX | BPF_PROBE_MEM | BPF_H:
+	case BPF_LDX | BPF_PROBE_MEM | BPF_B:
 		emit_a64_mov_i(1, tmp, off, ctx);
 		switch (BPF_SIZE(code)) {
 		case BPF_W:
@@ -753,6 +820,10 @@ emit_cond_jmp:
 			emit(A64_LDR64(dst, src, tmp), ctx);
 			break;
 		}
+
+		ret = add_exception_handler(insn, ctx, dst);
+		if (ret)
+			return ret;
 		break;
 
 	/* ST: *(size *)(dst + off) = imm */
@@ -868,6 +939,9 @@ static int validate_code(struct jit_ctx *ctx)
 			return -1;
 	}
 
+	if (WARN_ON_ONCE(ctx->exentry_idx != ctx->prog->aux->num_exentries))
+		return -1;
+
 	return 0;
 }
 
@@ -884,6 +958,7 @@ struct arm64_jit_data {
 
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 {
+	int image_size, prog_size, extable_size;
 	struct bpf_prog *tmp, *orig_prog = prog;
 	struct bpf_binary_header *header;
 	struct arm64_jit_data *jit_data;
@@ -891,7 +966,6 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	bool tmp_blinded = false;
 	bool extra_pass = false;
 	struct jit_ctx ctx;
-	int image_size;
 	u8 *image_ptr;
 
 	if (!prog->jit_requested)
@@ -922,7 +996,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		image_ptr = jit_data->image;
 		header = jit_data->header;
 		extra_pass = true;
-		image_size = sizeof(u32) * ctx.idx;
+		prog_size = sizeof(u32) * ctx.idx;
 		goto skip_init_ctx;
 	}
 	memset(&ctx, 0, sizeof(ctx));
@@ -950,8 +1024,12 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	ctx.epilogue_offset = ctx.idx;
 	build_epilogue(&ctx);
 
+	extable_size = prog->aux->num_exentries *
+		sizeof(struct exception_table_entry);
+
 	/* Now we know the actual image size. */
-	image_size = sizeof(u32) * ctx.idx;
+	prog_size = sizeof(u32) * ctx.idx;
+	image_size = prog_size + extable_size;
 	header = bpf_jit_binary_alloc(image_size, &image_ptr,
 				      sizeof(u32), jit_fill_hole);
 	if (header == NULL) {
@@ -962,8 +1040,11 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	/* 2. Now, the actual pass. */
 
 	ctx.image = (__le32 *)image_ptr;
+	if (extable_size)
+		prog->aux->extable = (void *)image_ptr + prog_size;
 skip_init_ctx:
 	ctx.idx = 0;
+	ctx.exentry_idx = 0;
 
 	build_prologue(&ctx, was_classic);
 
@@ -984,7 +1065,7 @@ skip_init_ctx:
 
 	/* And we're done. */
 	if (bpf_jit_enable > 1)
-		bpf_jit_dump(prog->len, image_size, 2, ctx.image);
+		bpf_jit_dump(prog->len, prog_size, 2, ctx.image);
 
 	bpf_flush_icache(header, ctx.image + ctx.idx);
 
@@ -1005,7 +1086,7 @@ skip_init_ctx:
 	}
 	prog->bpf_func = (void *)ctx.image;
 	prog->jited = 1;
-	prog->jited_len = image_size;
+	prog->jited_len = prog_size;
 
 	if (!prog->is_func || extra_pass) {
 		bpf_prog_fill_jited_linfo(prog, ctx.offset);